Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     territor
    -0.07
    	K
    -0.06
     comet
    -0.06
     vp
    -0.06
    JP
    -0.06
    _begin
    -0.06
    ctx
    -0.06
    oundary
    -0.06
    Kar
    -0.06
     Nadu
    -0.06
    POSITIVE LOGITS
    cke
    0.07
    _GREEN
    0.07
    ﻟ�
    0.06
    OLS
    0.06
     suffer
    0.06
    =BitConverter
    0.06
     كتاب
    0.06
    摄
    0.06
     chức
    0.06
    �ng
    0.06
    Act Density 0.018%

    No Known Activations